{
  // Temporal filters
  "date": "2024-11-14",
  "year": 2024,
  "month": 11,

  // Categorical filters
  "type": "bug_report",
  "category": "authentication",
  "severity": "high",

  // Numeric filters
  "citations": 42,
  "price": 150.25,
  "performance_score": 0.87,

  // Source tracking
  "source": "github_issue",
  "author": "kim-asplund",
  "url": "https://..."
}

// Step 1: Design collection strategy based on agent type
const collectionStrategy = {
  research_agent: "One collection per research topic/question",
  code_agent: "Collections by codebase module/feature",
  trading_agent: "Collections by strategy/timeframe/symbol",
  legal_agent: "Collections by practice area/jurisdiction",
  documentation_agent: "Collections by project/version"
};

// Step 2: Create collection with descriptive metadata
mcp__chroma__create_collection({
  collection_name: "{domain}_{purpose}_{identifier}",
  embedding_function_name: "default",  // Uses sentence transformers
  metadata: {
    created_date: "2024-11-14",
    domain: "research|code|trading|legal|docs",
    purpose: "Descriptive purpose",
    total_items: 0,  // Will update
    last_updated: "2024-11-14"
  }
});

// Step 1: Batch data collection (minimize API calls)
const items = collectAllItems();  // From API, files, database, etc.

// Step 2: Transform to ChromaDB format
const documents = items.map(item => formatDocument(item));
const ids = items.map(item => item.id || generateUniqueId());
const metadatas = items.map(item => extractMetadata(item));

// Step 3: Batch insert (ChromaDB handles chunking automatically)
mcp__chroma__add_documents({
  collection_name: collectionName,
  documents: documents,
  ids: ids,
  metadatas: metadatas
});

// Step 4: Update collection metadata
mcp__chroma__modify_collection({
  collection_name: collectionName,
  new_metadata: {
    ...existingMetadata,
    total_items: items.length,
    last_updated: new Date().toISOString()
  }
});

// Step 1: Formulate semantic query (natural language works!)
const query = "authentication failures in production environment";

// Step 2: Execute semantic search with filters
const results = mcp__chroma__query_documents({
  collection_name: collectionName,
  query_texts: [query],
  n_results: 20,
  where: {
    "$and": [
      { "environment": "production" },
      { "severity": { "$in": ["high", "critical"] } },
      { "date": { "$gte": "2024-01-01" } }
    ]
  },
  include: ["documents", "metadatas", "distances"]
});

// Step 3: Filter by semantic similarity (distance threshold)
const highlyRelevant = results.ids[0].filter((id, idx) =>
  results.distances[0][idx] < 0.3  // Adjust threshold based on use case
);

// Step 4: Retrieve full details if needed
const fullDetails = mcp__chroma__get_documents({
  collection_name: collectionName,
  ids: highlyRelevant,
  include: ["documents", "metadatas"]
});

// Cross-collection pattern detection
const allCollections = mcp__chroma__list_collections();
const relevantCollections = allCollections.filter(c =>
  c.startsWith(collectionPrefix)
);

const patterns = [];
for (const collection of relevantCollections) {
  const matches = mcp__chroma__query_documents({
    collection_name: collection,
    query_texts: [patternQuery],
    n_results: 10,
    where: { "outcome": "success" }  // Only successful cases
  });

  if (matches.ids[0].length > 0) {
    patterns.push({
      collection: collection,
      matches: matches,
      success_rate: calculateSuccessRate(matches)
    });
  }
}

// Identify best pattern
const bestPattern = patterns.sort((a, b) =>
  b.success_rate - a.success_rate
)[0];

// Collection: research_literature_{topic}
const papers = fetchPapersFromAPI("machine learning transformers");

mcp__chroma__create_collection({
  collection_name: "research_literature_ml_transformers",
  metadata: { topic: "ML Transformers", papers_count: 0 }
});

// Store papers with rich metadata
papers.forEach(paper => {
  mcp__chroma__add_documents({
    collection_name: "research_literature_ml_transformers",
    documents: [`${paper.title}. ${paper.abstract}`],
    ids: [paper.doi || paper.id],
    metadatas: [{
      title: paper.title,
      authors: paper.authors.join(", "),
      year: paper.year,
      citations: paper.citation_count,
      venue: paper.venue,
      url: paper.url
    }]
  });
});

// Semantic search: "Find papers about attention mechanisms for vision"
const relevant = mcp__chroma__query_documents({
  collection_name: "research_literature_ml_transformers",
  query_texts: ["attention mechanisms computer vision"],
  n_results: 20,
  where: { "year": { "$gte": 2020 }, "citations": { "$gte": 50 } }
});

// Collection: codebase_bug_patterns_{module}
const bugs = fetchAllGitHubIssues("is:issue label:bug");

mcp__chroma__create_collection({
  collection_name: "codebase_bug_patterns_auth",
  metadata: { module: "authentication", total_bugs: 0 }
});

// Store bugs with solutions
bugs.forEach(bug => {
  mcp__chroma__add_documents({
    collection_name: "codebase_bug_patterns_auth",
    documents: [`Bug #${bug.number}: ${bug.title}. ${bug.body}`],
    ids: [`bug_${bug.number}`],
    metadatas: [{
      number: bug.number,
      title: bug.title,
      severity: bug.labels.find(l => l.startsWith("severity:"))?.split(":")[1],
      status: bug.state,
      solution: bug.resolution || "No solution yet",
      created_at: bug.created_at,
      resolved_at: bug.closed_at,
      url: bug.html_url
    }]
  });
});

// New bug arrives - find similar historical bugs
const newBugDescription = "User login fails with 401 error after password reset";

const similarBugs = mcp__chroma__query_documents({
  collection_name: "codebase_bug_patterns_auth",
  query_texts: [newBugDescription],
  n_results: 10,
  where: { "status": "closed", "solution": { "$ne": "No solution yet" } }
});

// Extract solution from most similar resolved bug
const suggestedSolution = similarBugs.metadatas[0][0].solution;

// Collection: backtest_results_{strategy_name}
const backtests = runParameterSweep(strategyCode, parameterRanges);

mcp__chroma__create_collection({
  collection_name: "backtest_results_sma_crossover",
  metadata: { strategy: "SMA Crossover", total_backtests: 0 }
});

// Store each backtest with parameters + results
backtests.forEach(backtest => {
  const description = `
    SMA Crossover strategy with fast=${backtest.params.fast_period},
    slow=${backtest.params.slow_period}, stop_loss=${backtest.params.stop_loss}.
    Market conditions: ${backtest.market_regime}, volatility=${backtest.avg_volatility}.
  `;

  mcp__chroma__add_documents({
    collection_name: "backtest_results_sma_crossover",
    documents: [description],
    ids: [`backtest_${backtest.id}`],
    metadatas: [{
      fast_period: backtest.params.fast_period,
      slow_period: backtest.params.slow_period,
      stop_loss: backtest.params.stop_loss,
      sharpe_ratio: backtest.sharpe_ratio,
      max_drawdown: backtest.max_drawdown,
      win_rate: backtest.win_rate,
      total_return: backtest.total_return,
      market_regime: backtest.market_regime,
      symbol: backtest.symbol,
      timeframe: backtest.timeframe,
      start_date: backtest.start_date,
      end_date: backtest.end_date
    }]
  });
});

// Find optimal parameters for current market conditions
const currentMarket = analyzeCurrentMarket();
const marketDescription = `
  Market regime: ${currentMarket.regime}, volatility: ${currentMarket.volatility},
  trend strength: ${currentMarket.trend_strength}
`;

const optimalBacktests = mcp__chroma__query_documents({
  collection_name: "backtest_results_sma_crossover",
  query_texts: [marketDescription],
  n_results: 20,
  where: {
    "$and": [
      { "sharpe_ratio": { "$gte": 1.5 } },
      { "max_drawdown": { "$lte": -0.15 } },
      { "symbol": currentMarket.symbol }
    ]
  }
});

// Extract best parameter set
const bestParams = optimalBacktests.metadatas[0][0];

// Collection: api_docs_{project_version}
const existingDocs = parseAllApiDocs("./docs/api/");

mcp__chroma__create_collection({
  collection_name: "api_docs_v2",
  metadata: { version: "2.0", total_endpoints: 0 }
});

// Store documentation with style metadata
existingDocs.forEach(doc => {
  mcp__chroma__add_documents({
    collection_name: "api_docs_v2",
    documents: [doc.fullContent],
    ids: [doc.endpoint],
    metadatas: [{
      endpoint: doc.endpoint,
      method: doc.method,
      category: doc.category,
      style_score: doc.styleScore,  // Computed during ingestion
      has_examples: doc.examples.length > 0,
      has_error_codes: doc.errorCodes.length > 0,
      last_updated: doc.lastModified
    }]
  });
});

// New endpoint documented - find similar endpoints for style consistency
const newEndpoint = "POST /api/v2/users/{id}/preferences";

const similarEndpoints = mcp__chroma__query_documents({
  collection_name: "api_docs_v2",
  query_texts: [`${newEndpoint} user preferences update`],
  n_results: 5,
  where: {
    "$and": [
      { "method": "POST" },
      { "style_score": { "$gte": 0.9 } },
      { "has_examples": true }
    ]
  }
});

// Use similar endpoint as template
const template = similarEndpoints.documents[0][0];

// Collection: test_cases_{module}
const existingTests = parseTestFiles("./tests/");

mcp__chroma__create_collection({
  collection_name: "test_cases_authentication",
  metadata: { module: "authentication", total_tests: 0 }
});

// Store test cases with coverage metadata
existingTests.forEach(test => {
  mcp__chroma__add_documents({
    collection_name: "test_cases_authentication",
    documents: [`${test.description}. Covers: ${test.coveredScenarios.join(", ")}`],
    ids: [test.id],
    metadatas: [{
      test_type: test.type,  // "unit", "integration", "e2e"
      file_path: test.filePath,
      line_number: test.lineNumber,
      last_run: test.lastRun,
      status: test.lastStatus,
      execution_time_ms: test.executionTime,
      assertions: test.assertionCount
    }]
  });
});

// New feature added - identify missing test coverage
const newFeature = "Password reset with 2FA verification";

const existingCoverage = mcp__chroma__query_documents({
  collection_name: "test_cases_authentication",
  query_texts: [newFeature],
  n_results: 10
});

// If distance > 0.5, probably not covered
const isCovered = existingCoverage.distances[0][0] < 0.5;

if (!isCovered) {
  // Suggest test cases based on similar features
  const similarFeatures = mcp__chroma__query_documents({
    collection_name: "test_cases_authentication",
    query_texts: ["password reset", "2FA verification"],
    n_results: 5
  });

  // Use similar tests as templates
  const testTemplates = similarFeatures.documents[0];
}

// Example: Search all research topics for a cross-cutting concept
const researchCollections = mcp__chroma__list_collections();
const topicCollections = researchCollections.filter(c =>
  c.startsWith("research_literature_")
);

const crossTopicResults = [];
for (const collection of topicCollections) {
  const results = mcp__chroma__query_documents({
    collection_name: collection,
    query_texts: ["transfer learning"],
    n_results: 10
  });

  crossTopicResults.push({
    topic: collection.replace("research_literature_", ""),
    papers: results
  });
}

// Aggregate and rank by relevance across topics
const allPapers = crossTopicResults.flatMap(r =>
  r.papers.ids[0].map((id, idx) => ({
    id: id,
    topic: r.topic,
    distance: r.papers.distances[0][idx],
    metadata: r.papers.metadatas[0][idx]
  }))
);

const rankedPapers = allPapers.sort((a, b) => a.distance - b.distance);

// Parent: codebase_architecture_decisions
// Children: codebase_architecture_decisions_{year}

// Create parent collection with aggregated data
mcp__chroma__create_collection({
  collection_name: "codebase_architecture_decisions",
  metadata: { type: "parent", child_collections: [] }
});

// Create child collections by year
[2022, 2023, 2024].forEach(year => {
  mcp__chroma__create_collection({
    collection_name: `codebase_architecture_decisions_${year}`,
    metadata: { type: "child", parent: "codebase_architecture_decisions", year }
  });
});

// Query strategy: Try child first (faster), fallback to parent
const queryYear = 2024;
let results = mcp__chroma__query_documents({
  collection_name: `codebase_architecture_decisions_${queryYear}`,
  query_texts: [query],
  n_results: 10
});

if (results.ids[0].length < 5) {
  // Not enough results in child, query parent
  results = mcp__chroma__query_documents({
    collection_name: "codebase_architecture_decisions",
    query_texts: [query],
    n_results: 10
  });
}

// Store items with temporal metadata
mcp__chroma__add_documents({
  collection_name: collectionName,
  documents: documents,
  ids: ids,
  metadatas: metadatas.map(m => ({
    ...m,
    timestamp: Date.now(),
    age_days: 0  // Will be updated
  }))
});

// Query with temporal boost
const results = mcp__chroma__query_documents({
  collection_name: collectionName,
  query_texts: [query],
  n_results: 50  // Get more results for re-ranking
});

// Re-rank with temporal decay
const now = Date.now();
const rankedResults = results.ids[0].map((id, idx) => {
  const ageDays = (now - results.metadatas[0][idx].timestamp) / (1000 * 60 * 60 * 24);
  const decayFactor = Math.exp(-ageDays / 30);  // Half-life ~30 days
  const semanticScore = 1 - results.distances[0][idx];
  const combinedScore = semanticScore * 0.7 + decayFactor * 0.3;

  return {
    id: id,
    semantic_score: semanticScore,
    decay_factor: decayFactor,
    combined_score: combinedScore,
    metadata: results.metadatas[0][idx]
  };
}).sort((a, b) => b.combined_score - a.combined_score);

// BAD: One document at a time (slow)
for (const item of items) {
  mcp__chroma__add_documents({
    collection_name: collectionName,
    documents: [item.document],
    ids: [item.id],
    metadatas: [item.metadata]
  });
}

// GOOD: Batch insert (100x faster)
const BATCH_SIZE = 100;
for (let i = 0; i < items.length; i += BATCH_SIZE) {
  const batch = items.slice(i, i + BATCH_SIZE);
  mcp__chroma__add_documents({
    collection_name: collectionName,
    documents: batch.map(item => item.document),
    ids: batch.map(item => item.id),
    metadatas: batch.map(item => item.metadata)
  });
}